Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Automation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,765 records · Page 98

Sensitive and Specific Peak Detection for SELDI-TOF Mass Spectrometry Using a Wavelet/Neural-Network Based Approach

SELDI-TOF mass spectrometer’s compact size and automated, high throughput design have been attractive to clinical researchers, and the platform has seen steady-use in biomarker studies. Despite new algorithms and preprocessing pipelines that have been developed to address reproducibility issues, visual inspection of the results of SELDI spectra preprocessing by the best algorithms still shows miscalled peaks and systematic sources of error. This suggests that there continues to be problems with SELDI preprocessing. In this work, we study the preprocessing of SELDI in detail and introduce improvements. While many algorithms, including the vendor supplied software, can identify peak clusters of specific mass (or m/z) in groups of spectra with high specificity and low false discover rate (FDR), the algorithms tend to underperform estimating the exact prevalence and intensity of peaks in those clusters. Thus group differences that at first appear very strong are shown, after careful and laborious hand inspection of the spectra, to be less than significant. Here we introduce a wavelet/neural network based algorithm which mimics what a team of expert, human users would call for peaks in each of several hundred spectra in a typical SELDI clinical study. The wavelet denoising part of the algorithm optimally smoothes the signal in each spectrum according to an improved suite of signal processing algorithms previously reported (the LibSELDI toolbox under development). The neural network part of the algorithm combines those results with the raw signal and a training dataset of expertly called peaks, to call peaks in a test set of spectra with approximately 95% accuracy. The new method was applied to data collected from a study of cervical mucus for the early detection of cervical cancer in HPV infected women. The method shows promise in addressing the ongoing SELDI reproducibility issues.

59 BASIC BIOLOGICAL SCIENCES↗

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields, in part due to a culture of open data sharing and reuse. AI/ML methodology is well-suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Inexperienced researchers can produce models that perform poorly outside of the training dataset. Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Casaletto↗

Distributed Scheduling Architecture for Multi-Center Time-Based Metering

The Traffic Management Advisor (TMA) is an air traffic control automation system currently in use in seven Air Route Traffic Control Centers (ARTCCs) to enable time based metering to busy airports within their airspace. However, this system is limited to operation within a single ARTCC, within about a 200 nautical mile radius of the airport, and on relatively simple streams of traffic. The need for coordinated metering within a greater (300+ nautical mile) radius of an airport, on streams of traffic with significant branching, and across ARTCC boundaries, has been identified. Early tests revealed that TMA could not simply be scaled up to handle such a problem. Instead, a loosely coupled hierarchy of schedules, in which constraints from downstream schedules are passed upstream, is required. Such an architecture reduces the reliance on distant projections of arrival times, making schedules robust to changes in sequence and to additions of aircraft (such as aircraft departing inside the system s scheduling horizon). This architecture is also scaleable, easily reconfigurable, and can be networked together. As such, it can be adapted for use in any size or configuration of airspace and with any number of airports delivering restrictions. An implementation of this distributed scheduling architecture is currently undergoing testing in the TMA-Multi Center system. This paper describes the architecture and its motivation.

Landry, Steven↗

High-performance mass storage system for workstations

Reduced Instruction Set Computer (RISC) workstations and Personnel Computers (PC) are very popular tools for office automation, command and control, scientific analysis, database management, and many other applications. However, when using Input/Output (I/O) intensive applications, the RISC workstations and PC's are often overburdened with the tasks of collecting, staging, storing, and distributing data. Also, by using standard high-performance peripherals and storage devices, the I/O function can still be a common bottleneck process. Therefore, the high-performance mass storage system, developed by Loral AeroSys' Independent Research and Development (IR&D) engineers, can offload a RISC workstation of I/O related functions and provide high-performance I/O functions and external interfaces. The high-performance mass storage system has the capabilities to ingest high-speed real-time data, perform signal or image processing, and stage, archive, and distribute the data. This mass storage system uses a hierarchical storage structure, thus reducing the total data storage cost, while maintaining high-I/O performance. The high-performance mass storage system is a network of low-cost parallel processors and storage devices. The nodes in the network have special I/O functions such as: SCSI controller, Ethernet controller, gateway controller, RS232 controller, IEEE488 controller, and digital/analog converter. The nodes are interconnected through high-speed direct memory access links to form a network. The topology of the network is easily reconfigurable to maximize system throughput for various applications. This high-performance mass storage system takes advantage of a 'busless' architecture for maximum expandability. The mass storage system consists of magnetic disks, a WORM optical disk jukebox, and an 8mm helical scan tape to form a hierarchical storage structure. Commonly used files are kept in the magnetic disk for fast retrieval. The optical disks are used as archive media, and the tapes are used as backup media. The storage system is managed by the IEEE mass storage reference model-based UniTree software package. UniTree software will keep track of all files in the system, will automatically migrate the lesser used files to archive media, and will stage the files when needed by the system. The user can access the files without knowledge of their physical location. The high-performance mass storage system developed by Loral AeroSys will significantly boost the system I/O performance and reduce the overall data storage cost. This storage system provides a highly flexible and cost-effective architecture for a variety of applications (e.g., realtime data acquisition with a signal and image processing requirement, long-term data archiving and distribution, and image analysis and enhancement).

Chiang, T.↗

Inspection and Verification of Domain Models with PlanWorks and Aver

When developing a domain model, it seems natural to bring the traditional informal tools of inspection and verification, debuggers and automated test suites, to bear upon the problems that will inevitably arise. Debuggers that allow inspection of registers and memory and stepwise execution have been a staple of software development of all sorts from the very beginning. Automated testing has repeatedly proven its considerable worth, to the extent that an entire design philosophy (Test Driven Development) has been developed around the writing of tests. Unfortunately, while not entirely without their uses, the limitations of these tools and the nature of the complexity of models and the underlying planning systems make the diagnosis of certain classes of problems and the verification of their solutions difficult or impossible. Debuggers provide a good local view of executing code, allowing a fine-grained look at algorithms and data. This view is, however, usually only at the level of the current scope in the implementation language, and the data-inspection capabilities of most debuggers usually consist of on-line print statements. More modem graphical debuggers offer a sort of tree view of data structures, but even this is too low-level and is often inappropriate for the kinds of structures created by planning systems. For instance, god or constraint networks are at best awkward when visualized as trees. Any any non-structural link between data structures, as through a lookup table, isn't captured at all. Further, while debuggers have powerful breakpointing facilities that are suitable for finding specific algorithmic errors, they have little use in the diagnosis of modeling errors.

Bedrax-Weiss, Tania↗

Artificial Intelligence and Computer Vision for Cost-Effective Benthic Habitat Characterizations

Machine learning applied to computer vision and pattern recognition is a type of artificial intelligence that has advanced rapidly in the last 10 to 15 years, spurred forward by breakthroughs in deep convolutional neural networks. These state-of-the-art methods are poised to become widely used in environmental monitoring applications as a result of the increasing abundance of data available from different imaging platforms (e.g., fixed-point cameras, drone surveys, high-resolution satellite data) that can be analyzed to observe, model, and understand environmental conditions. Computer vision and pattern recognition (CVPR) tools advance our ability to use imagery and camera-based tools in cost-effective ways for environmental monitoring. Although these techniques offer great potential, some challenges remain, such as the need for large sets of labeled images for model training and validation and optimized hardware and software to ensure that the models can be trained effectively and in a reasonable amount of time. Here, we have overcome many of these rate-limiting challenges by using a diverse image library built across multiple projects coupled with staff expertise and onsite computing resources. We are working toward a fully automated SPI processing system and also are moving to develop CVPR analytical tools for other imaging platforms and data sets.

02 PETROLEUM↗

Chemical, Biological, and Explosive Sensors for Field Measurements

Special Technologies Laboratory (STL) is developing handheld chemical, biological, and explosive (CBE) detection systems and sensor motes for wireless networked field operations. The CBE sensors are capable of detecting and identifying multiple targeted toxic industrial chemicals (TICs) and high-explosive vapor components. The CBE devices are based on differential mobility spectrometry (DMS) coupled with fast gas chromatography (GC) or mass spectrometry. The systems all include the concepts of: 1. Direct air/particulate “smart” sampling 2. Selective, continuous real-time (~1 sec) alert monitoring using DMS 3. Highly selective, rapid dual technology separation/verification analysis The biosensor technology is based on Raman aerosol particle flow cytometry for target detection and identification. Monitoring and identifying trace level chemical vapors directly from ambient air will allow First Responders to quickly adapt situational response strategies and personal protective equipment needs to the specific response scenario being encountered. First Responders require great confidence in the measurements and ability of a given system to detect CBE below threshold levels without interferences. The concept of determining the background matrix in near real-time to allow subsequent automated field-programmable method selection and cueing of high-value assets in a wide range of environs will be presented. This provides CBE information for decisions prior to First Responders entering the response site or sending a portable mobile unit for a remote site survey of the hazards. The focus is on real-time information needed by those responsible for emergency response and national security.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Multiplexer/Demultiplexer Loading Tool (MDMLT)

The purpose of the MDMLT is to improve the reliability and speed of loading multiplexers/demultiplexers (MDMs) in the Software Development and Integration Laboratory (SDIL) by automating the configuration management (CM) of the loads in the MDMs, automating the loading procedure, and providing the capability to load multiple or all MDMs concurrently. This loading may be accomplished in parallel, or single MDMs (remote). The MDMLT is a Web-based tool that is capable of loading the entire International Space Station (ISS) MDM configuration in parallel. It is able to load Flight Equivalent Units (FEUs), enhanced, standard, and prototype MDMs as well as both EEPROM (Electrically Erasable Programmable Read-Only Memory) and SSMMU (Solid State Mass Memory Unit) (MASS Memory). This software has extensive configuration management to track loading history, and the performance improvement means of loading the entire ISS MDM configuration of 49 MDMs in approximately 30 minutes, as opposed to 36 hours, which is what it took previously utilizing the flight method of S-Band uplink. The laptop version recently added to the MDMLT suite allows remote lab loading with the CM of information entered into a common database when it is reconnected to the network. This allows the program to reconfigure the test rigs quickly between shifts, allowing the lab to support a variety of onboard configurations during a single day, based on upcoming or current missions. The MDMLT Computer Software Configuration Item (CSCI) supports a Web-based command and control interface to the user. An interface to the SDIL File Transfer Protocol (FTP) server is supported to import Integrated Flight Loads (IFLs) and Internal Product Release Notes (IPRNs) into the database. An interface to the Monitor and Control System (MCS) is supported to control the power state, and to enable or disable the debug port of the MDMs to be loaded. Two direct interfaces to the MDM are supported: a serial interface (debug port) to receive MDM memory dump data and the calculated checksum, and the Small Computer System Interface (SCSI) to transfer load files to MDMs with hard disks. File transfer from the MDM Loading Tool to EEPROM within the MDM is performed via the MILSTD- 1553 bus, making use of the Real- Time Input/Output Processors (RTIOP) when using the rig-based MDMLT, and via a bus box when using the laptop MDMLT. The bus box is a cost-effective alternative to PC-1553 cards for the laptop. It is noted that this system can be modified and adapted to any avionic laboratory for spacecraft computer loading, ship avionics, or aircraft avionics where multiple configurations and strong configuration management of software/firmware loads are required.

Brewer, Lenox Allen↗

A Natural Language Understanding Approach for Digitizing Aircraft Ground Taxi Instructions

Recent Advancements in spoken language processing technologies have enabled the development of reliable automation tools to assist air traffic control (ATC) operations. These advancements present a unique opportunity to strategically implement digital taxi instructions for aircraft movement on the ground. Digital taxi instructions issue taxiing procedures to pilots as textual or graphical instructions. There are several benefits of digital instructions, including a reduction in radio congestion, elimination of communication errors, and improved aircraft monitoring capabilities. Natural language understanding (NLU) models can extract digital taxi instructions from verbal instructions issued by air traffic controllers. This capability enables the implementation of a digital taxi communication framework with minimal changes to the existing air traffic controller operational environment. We explore a novel application for NLU: automatically generating digital taxi instructions from air traffic controller speech. We describe the development of an annotation scheme to represent (aircraft) ground traffic communications in the US National Airspace System (NAS).Our annotation scheme uses intent classification and slot filling to extract taxi instructions, enabling NLU models to leverage syntactic information. Several neural network models were trained to categorize the controller’s intent and label information relevant to his or her intent.Our research demonstrates that it is feasible to use NLU to automatically generate digitaltaxi instructions, suggesting that it is a powerful tool for the implementation of digital taxi communications.

Hillel Steinmetz↗

FINAL TECHNICAL REPORT: Underwater Active Acoustic Monitoring Network For Marine And Hydrokinetic Energy Projects

This project saw the completion of the design and development of a second generation, high frequency (90-120 kHz) Subsurface-Threat Detection Sonar Network (SDSN). The system was deployed, operated, and tested in Cobscook Bay, Maine near the site the Ocean Renewable Power Company TidGen™ power unit. This effort resulted in a very successful demonstration of the SDSN detection, tracking, localization, and classification capabilities in a high current, MHK environment as measured by results from the detection and tracking trials in Cobscook Bay. The new high frequency node, designed to operate outside the hearing range of a subset of marine mammals, was shown to detect and track objects of marine mammal-like target strength to ranges of approximately 500 meters. This performance range results in the SDSN system tracking objects for a significant duration - on the order of minutes - even in a tidal flow of 5-7 knots, potentially allowing time for MHK system or operator decision-making if marine mammals are present. Having demonstrated detection and tracking of synthetic targets with target strengths similar to some marine mammals, the primary hurdle to eventual automated monitoring is a dataset of actual marine mammal kinematic behavior and modifying the tracking algorithms and parameters which are currently tuned to human diver kinematics and classification.

16 TIDAL AND WAVE POWER↗

CyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model

We introduce CyBERT, a cybersecurity feature claims classifier based on bidirectional encoder representations from transformers and a key component in our semi-automated cybersecurity vetting for industrial control systems (ICS). To train CyBERT, we created a corpus of labeled sequences from ICS device documentation collected across a wide range of vendors and devices. This corpus provides the foundation for fine-tuning BERT’s language model, including a prediction-guided relabeling process. We propose an approach to obtain optimal hyperparameters, including the learning rate, the number of dense layers, and their configuration, to increase the accuracy of our classifier. Fine-tuning all hyperparameters of the resulting model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original architecture to 94.4% obtained with CyBERT. Furthermore, we evaluated CyBERT for the impact of randomness in the initialization, training, and data-sampling phases. CyBERT demonstrated a standard deviation of ±0.6% during validation across 100 random seed values. Finally, we also compared the performance of CyBERT to other well-established language models including GPT2, ULMFiT, and ELMo, as well as neural network models such as CNN, LSTM, and BiLSTM. The results showed that CyBERT outperforms these models on the validation accuracy and the F1 score, validating CyBERT’s robustness and accuracy as a cybersecurity feature claims classifier.

97 MATHEMATICS AND COMPUTING↗

Extension and Validation of NEMA-Style Dual-Ring Controller in SUMO

Until recently, SUMO users could not model the behavior of a ring-and-barrier traffic signal via existing signal types, which left North American SUMO users without the direct ability to capture traffic dynamics of their local networks. This work presents the methods, implementation overview, and validation of a 'dual-ring' NEMA style traffic controller which has recently been added to the main SUMO code base. A brief explanation of the 'dual-ring' implementation is also provided as context for those new to this type of traffic controller. The foundation for this work was presented at the SUMO User Conference 2021 by researchers at the US Department of Energy's National Renewable Energy Laboratory, but was not integrated into SUMO code base at the time. Following the initial inclusion of the controller to SUMO, the authors began validation of the SUMO controller against an Econolite software-in-the-loop (SIL) traffic signal controller configured with actual setup parameters from controllers in a real-world three-intersection corridor in Tuscaloosa, Alabama, USA. This paper documents the process of adding new features to the controller code as well as validating their implementation through simulation-based and automated grey-box testing is presented in this paper. Key features such as fully-actuated operation, various timing offset plans, proper next-phase fit algorithms and more, have been added and validated against this SIL system. Though not an exhaustive demonstration of features, this work is intended make more users aware of this extension of SUMO capabilities.

MATHEMATICS AND COMPUTING↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

SU-E-T-465: Implementation of An Automated Collision Detection Program Using Open Source Software for the Pinnacle Treatment Planning System

Purpose: Potential collisions between the gantry head and the patient or table assembly are difficult to detect in most treatment planning systems. We have developed and implemented a novel software package for the representation of potential gantry collisions with the couch assembly at the time of treatment planning. Methods: Physical dimensions of the Varian Edge linear accelerator treatment head were measured and reproduced using the Visual Python display package. A script was developed for the Pinnacle treatment planning system to generate a file with the relevant couch, gantry, and isocenter positions for each beam in a planning trial. A python program was developed to parse the information from the TPS and produce a representative model of the couch/gantry system. Using the model and the Visual Python libraries, a rendering window is generated for each beam that allows the planner to evaluate the possibility of a collision. Results: Comparison against heuristic methods and direct verification on the machine validated the collision model generated by the software. Encounters of <1 cm between the gantry treatment head and table were visualized as collisions in our virtual model. Visual windows were created depicting the angle of collision for each beam, including the anticipated table coordinates. Visual rendering of a 6 arc trial with multiple couch positions was completed in under 1 minute, with network bandwidth being the primary bottleneck. Conclusion: The developed software allows for quick examination of possible collisions during the treatment planning process and helps to prevent major collisions prior to plan approval. The software can easily be implemented on future planning systems due to the versatility and platform independence of the Python programming language. Further integration of the software with the treatment planning system will allow the possibility of patient-gantry collision detection for a range of treatment machines.

60 APPLIED LIFE SCIENCES↗

Is infrared-collinear safe information all you need for jet classification?

Machine learning-based jet classifiers are able to achieve impressive tagging performance in a variety of applications in high-energy and nuclear physics. However, it remains unclear in many cases which aspects of jets give rise to this discriminating power, and whether jet observables that are tractable in perturbative QCD such as those obeying infrared-collinear (IRC) safety serve as sufficient inputs. In this article, we introduce a new classifier, Jet Flow Networks (JFNs), in an effort to address the question of whether IRC unsafe information provides additional discriminating power in jet classification. JFNs are permutation-invariant neural networks (deep sets) that take as input the kinematic information of reconstructed subjets. The subjet radius and a cut on the subjet’s transverse momenta serve as tunable hyperparameters enabling a controllable sensitivity to soft emissions and nonperturbative effects. We demonstrate the performance of JFNs for quark vs. gluon and Z vs. QCD jet tagging. For small subjet radii and transverse momentum cuts, the performance of JFNs is equivalent to the IRC-unsafe Particle Flow Networks (PFNs), demonstrating that infrared-collinear unsafe information is not necessary to achieve strong discrimination for both cases. As the subjet radius is increased, the performance of the JFNs remains essentially unchanged until physical thresholds that we identify are crossed. For relatively large subjet radii, we show that the JFNs may offer an increased model independence with a modest tradeoff in performance compared to classifiers that use the full particle information of the jet. These results shed new light on how machines learn patterns in high-energy physics data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Seismic Waveform Inversion Capability on Resource-Constrained Edge Devices

Seismic full wave inversion (FWI) is a widely used non-linear seismic imaging method used to reconstruct subsurface velocity images, however it is time consuming, has high computational cost and depend heavily on human interaction. Recently, deep learning has accelerated it’s use in several data-driven techniques, however most deep learning techniques suffer from overfitting and stability issues. In this work, we propose an edge computing-based data-driven inversion technique based on supervised deep convolutional neural network to accurately reconstruct the subsurface velocities. Deep learning based data-driven technique depends mostly on bulk data training. In this work, we train our deep convolutional neural network (DCN) (UNet and InversionNet) on the raw seismic data and their corresponding velocity models during the training phase to learn the non-linear mapping between the seismic data and velocity models. The trained network is then used to estimate the velocity models from new input seismic data during the prediction phase. The prediction phase is performed on a resource-constrained edge device such as Raspberry Pi. Raspberry Pi provides real-time and on-device computational power to execute the inference process. In addition, we demonstrate robustness of our models to perform inversion in the presence on noise by performing both noise-aware and no-noise training and feeding the resulting trained models with noise at different signal-to-noise (SNR) ratio values. We make great efforts to achieve very feasible inference times on the Raspberry Pi for both models. Specifically, the inference times per prediction for UNet and InversionNet models on Raspberry Pi were 22 and 4 s respectively whilst inference times for both models on the GPU were 2 and 18 s which are very comparable. Finally, we have designed a user-friendly interactive graphical user interface (GUI) to automate the model execution and inversion process on the Raspberry Pi.

Manu, Daniel (ORCID:0000000154982677)↗

WE-A-18A-01: TG246 On Patient Dose From Diagnostic Radiation

Radiation dose from diagnostic and interventional radiations continues to be a focus of the regulatory, accreditation and standards organizations in the US and Europe. A Joint AAPM/EFOMP effort has been underway in the past year — having the goal to assist the clinical medical physicist with communicating optional and varied approaches in estimating (and validating) patient dose. In particular, the tools provided by DICOM Radiation Dose Structured Reports, either by themselves or as part of a networked data repository of dose related information are a rich source of actionable information. The tools of the medical physicist have evolved to include using DICOM data in meaningful ways to look at patient dose with respect to imaging practices. In addition to how accurate or reproducible a dose value is (totally necessary and our traditional workspace) it is now being asked how reproducible (patient to patient, device to device) are the delivered doses (new tasking)? Clinical medical physicists are best equipped to assist our radiology and technologist colleagues with this effort. The purpose of this session is to review the efforts of TG246 - bringing forward a summary content of the TG246 Report including specific dose descriptors for CT and Fluoroscopy — particularly in a focus of leveraging the RDSR as a means for monitoring good practices ALARA. Additionally, rapidly evolving technologies for more refined dose estimates are now in use. These will be presented as they look to having highly patient specific dose estimates in automated use.

60 APPLIED LIFE SCIENCES↗